List your company

Tool Use on Aggregate Performance

76.8Avg1 ScoreNRE
-1.40818.89639.259.504Jul 5, 2026

Evaluation results

MethodLinks
NREModel=Kimi-k2.62026.0776.879.9
VanillaModel=Opus 4.72026.0776.778.1
NREModel=Haiku 4.52026.0775.979
NREModel=Mistral 3.52026.077577.5
VanillaModel=Sonnet 4.62026.0774.576.2
NREModel=gpt-5.4-mini2026.0772.976
NREModel=gpt-oss-120b2026.0772.777
NREModel=Deepseek-v32026.0772.475.2
VanillaModel=Kimi-k2.62026.0772.373.2
GEPAModel=Kimi-k2.62026.0771.274.1
VanillaModel=Haiku 4.52026.0759.261.1
RLMModel=Kimi-k2.62026.0757.859.8
GEPAModel=gpt-oss-120b2026.0756.659.4
VanillaModel=Deepseek-v32026.0754.757.2
VanillaModel=gpt-oss-120b2026.0751.252.7
VanillaModel=Deepseek-R12026.0738.441.5
GEPAModel=Deepseek-v32026.0735.738.2
VanillaModel=gpt-5.4-mini2026.0734.937.9
RLMModel=gpt-oss-120b2026.0722.124.2
RLMModel=Deepseek-v32026.071.62.4